{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DRLOER4XUL76JLLJSOOWSA7MWM","short_pith_number":"pith:DRLOER4X","schema_version":"1.0","canonical_sha256":"1c56e24797a2ffe4ad69939d6903ecb33598926d8a7f419d4536fa5be57626f4","source":{"kind":"arxiv","id":"2411.01156","version":2},"attestation_state":"computed","paper":{"title":"Fish-Speech: Leveraging Large Language Models for Advanced Multilingual Text-to-Speech Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Rongzhi Zhou, Ruoyi Zhang, Shijia Liao, Tianyu Li, Yifan Cheng, Yijin Xing, Yuxuan Wang","submitted_at":"2024-11-02T07:04:02Z","abstract_excerpt":"Text-to-Speech (TTS) systems face ongoing challenges in processing complex linguistic features, handling polyphonic expressions, and producing natural-sounding multilingual speech - capabilities that are crucial for future AI applications. In this paper, we present Fish-Speech, a novel framework that implements a serial fast-slow Dual Autoregressive (Dual-AR) architecture to enhance the stability of Grouped Finite Scalar Vector Quantization (GFSQ) in sequence generation tasks. This architecture improves codebook processing efficiency while maintaining high-fidelity outputs, making it particula"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2411.01156","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-11-02T07:04:02Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"7a31fa4e4932260da12a428c834bedd73d1691275ad728d40de2d8e1aff4df18","abstract_canon_sha256":"478757af28fb81d26e888f9962824b8063d71a002557dd0978d8c5f983506273"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:33:10.912806Z","signature_b64":"IjKVeZqD0xTYbZ0PHrBFP00DIp5BH/GSApI/4eZhG+AEkdJOXx696dUIhZYpf2UtoP5VXJ6AWkKMPBVM9JuNBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c56e24797a2ffe4ad69939d6903ecb33598926d8a7f419d4536fa5be57626f4","last_reissued_at":"2026-07-05T09:33:10.912291Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:33:10.912291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fish-Speech: Leveraging Large Language Models for Advanced Multilingual Text-to-Speech Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Rongzhi Zhou, Ruoyi Zhang, Shijia Liao, Tianyu Li, Yifan Cheng, Yijin Xing, Yuxuan Wang","submitted_at":"2024-11-02T07:04:02Z","abstract_excerpt":"Text-to-Speech (TTS) systems face ongoing challenges in processing complex linguistic features, handling polyphonic expressions, and producing natural-sounding multilingual speech - capabilities that are crucial for future AI applications. In this paper, we present Fish-Speech, a novel framework that implements a serial fast-slow Dual Autoregressive (Dual-AR) architecture to enhance the stability of Grouped Finite Scalar Vector Quantization (GFSQ) in sequence generation tasks. This architecture improves codebook processing efficiency while maintaining high-fidelity outputs, making it particula"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.01156","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2411.01156/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2411.01156","created_at":"2026-07-05T09:33:10.912378+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.01156v2","created_at":"2026-07-05T09:33:10.912378+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.01156","created_at":"2026-07-05T09:33:10.912378+00:00"},{"alias_kind":"pith_short_12","alias_value":"DRLOER4XUL76","created_at":"2026-07-05T09:33:10.912378+00:00"},{"alias_kind":"pith_short_16","alias_value":"DRLOER4XUL76JLLJ","created_at":"2026-07-05T09:33:10.912378+00:00"},{"alias_kind":"pith_short_8","alias_value":"DRLOER4X","created_at":"2026-07-05T09:33:10.912378+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":17,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21343","citing_title":"An Evaluation Framework for Text-to-Speech Voice Reconstruction","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09141","citing_title":"FlashTTS: Fast Streaming TTS with MTP Acceleration and X-pred Mean Flow Distillation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30993","citing_title":"SwanVoice: Expressive Long-Form Zero-Shot Speech Synthesis for Both Monologue and Dialogue","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31173","citing_title":"MindVoice: Reconstructing Intelligible Speech from Non-invasive Neural Signals with Pretrained Priors","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31247","citing_title":"FlexiSLM: A Dynamic and Controllable Frame Rate Spoken Language Model","ref_index":95,"is_internal_anchor":false},{"citing_arxiv_id":"2510.19414","citing_title":"EchoFake: A Replay-Aware Dataset for Practical Speech Deepfake Detection","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2510.01284","citing_title":"Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2601.15621","citing_title":"Qwen3-TTS Technical Report","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2603.02364","citing_title":"When Spoof Detectors Travel: Evaluation Across 66 Languages in the Low-Resource Language Spoofing Corpus","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2604.00688","citing_title":"OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12310","citing_title":"Poly-SVC: Polyphony-Aware Singing Voice Conversion with Harmonic Modeling","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02374","citing_title":"Evaluating Generalization and Robustness in Russian Anti-Spoofing: The RuASD Initiative","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23742","citing_title":"RTCFake: Speech Deepfake Detection in Real-Time Communication","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24794","citing_title":"V.O.I.C.E (Voice, Ownership, Identity, Control, Expression): Risk Taxonomy of Synthetic Voice Generation From Empirical Data","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01638","citing_title":"Omni-Fake: Benchmarking Unified Multimodal Social Media Deepfake Detection","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11283","citing_title":"Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented Survey","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16211","citing_title":"NVBench: A Benchmark for Speech Synthesis with Non-Verbal Vocalizations","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DRLOER4XUL76JLLJSOOWSA7MWM","json":"https://pith.science/pith/DRLOER4XUL76JLLJSOOWSA7MWM.json","graph_json":"https://pith.science/api/pith-number/DRLOER4XUL76JLLJSOOWSA7MWM/graph.json","events_json":"https://pith.science/api/pith-number/DRLOER4XUL76JLLJSOOWSA7MWM/events.json","paper":"https://pith.science/paper/DRLOER4X"},"agent_actions":{"view_html":"https://pith.science/pith/DRLOER4XUL76JLLJSOOWSA7MWM","download_json":"https://pith.science/pith/DRLOER4XUL76JLLJSOOWSA7MWM.json","view_paper":"https://pith.science/paper/DRLOER4X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.01156&json=true","fetch_graph":"https://pith.science/api/pith-number/DRLOER4XUL76JLLJSOOWSA7MWM/graph.json","fetch_events":"https://pith.science/api/pith-number/DRLOER4XUL76JLLJSOOWSA7MWM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DRLOER4XUL76JLLJSOOWSA7MWM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DRLOER4XUL76JLLJSOOWSA7MWM/action/storage_attestation","attest_author":"https://pith.science/pith/DRLOER4XUL76JLLJSOOWSA7MWM/action/author_attestation","sign_citation":"https://pith.science/pith/DRLOER4XUL76JLLJSOOWSA7MWM/action/citation_signature","submit_replication":"https://pith.science/pith/DRLOER4XUL76JLLJSOOWSA7MWM/action/replication_record"}},"created_at":"2026-07-05T09:33:10.912378+00:00","updated_at":"2026-07-05T09:33:10.912378+00:00"}